Back to leaderboard

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
82 vs 76
Hardware Fit
88 vs 100
Quality Score
80 vs 66

Hardware

unsloth-phi-4 hf.co/empero-ai/Qw…
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM64 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.7.4macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

unsloth-phi-4 hf.co/empero-ai/Qw…
Tokens/sec27.440.3
First chunk457 ms101 ms
TTFT457 ms101 ms
Load timeN/A2.7 s
Memory usage7.7 GB4.5 GB
Memory %12%28%

HW Fit Score Breakdown

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

hf.co/empero-ai/Qwen3.8…

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

hf.co/empero-ai/Qwen3.8…

Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View unsloth-phi-4 details | View hf.co/empero-ai/Qw… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest